The scatter in the galaxy-halo connection: a machine learning analysis

Abstract

We apply machine learning, a powerful method for uncovering complex correlations in high-dimensional data, to the galaxyhalo connection of cosmological hydrodynamical simulations. The mapping between galaxy and halo variables is stochastic in the absence of perfect information, but conventional machine learning models are deterministic and hence cannot capture its intrinsic scatter. To overcome this limitation, we design an ensemble of neural networks with a Gaussian loss function that predict probability distributions, allowing us to model statistical uncertainties in the galaxy-halo connection as well as its best-fit trends. We extract a number of galaxy and halo variables from the Horizon-AGN and IllustrisTNG100-1 simulations and quantify the extent to which knowledge of some subset of one enables prediction of the other. This allows us to identify the key features of the galaxy-halo connection and investigate the origin of its scatter in various projections. We find that while halo properties beyond mass account for up to 50 per cent of the scatter in the halo-to-stellar mass relation, the prediction of stellar half-mass radius or total gas mass is not substantially improved by adding further halo properties. We also use these results to investigate semi-analytic models for galaxy size in the two simulations, finding that assumptions relating galaxy size to halo size or spin are not successful.

KLLR: A Scale-dependent, Multivariate Model Class for Regression Analysis

“…Parameter-free models, such as Bayesian additive regression trees (Hill et al 2020), Gaussian processes (Alvarez et al 2011), ensemble tree models (Chen & Guestrin 2016), and neural networks (Rumelhart et al 1986), have emerged as an alternative to fully specified models (e.g., Green et al 2019;de Souza et al 2021;Machado Poletti Valle et al 2021;Ntampaka & Vikhlinin 2022;Stiskalek et al 2022). Despite the unmatched success of these models in making accurate predictions, their applications to physical sciences, including astronomy, can be limited by their interpretability (Ntampaka & Vikhlinin 2022).…”